Synthometricon

Synthometricon

Search a collection of over 71,000 scales gathered from more than 28,000 tests, surveys and questionnaires. Built for researchers in the behavioral sciences and run as a Docker app.

Made by magnolia-psychometrics on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Synthometricon is a search engine for psychological and behavioral measures. Its collection holds over 71,000 scales, gathered from more than 28,000 tests, surveys and questionnaires that were already published. It belongs to a research project that brings large language models into scientific workflows, to cut the burden on researchers and make results easier to repeat.

Who it suits: Researchers who need to know whether a scale for their concept already exists before they build a new one. Survey and test designers can use it to see what has been published.

Industry | Who uses it | How they use it | Example
Behavioral science | Psychology researchers | Search for existing scales that cover a concept | Checking whether a measure for a trait is already published
Survey design | Survey designers | Look at published questionnaires before writing items | Comparing how earlier studies asked about the same topic
Test development | Test developers | Find related scales to place a new test among them | Looking for scales that overlap with a draft questionnaire
Research methods | Meta-researchers | Study overlap between measures across the literature | Looking at how many scales name the same idea

If you do not work with questionnaires or measures, you can skip it.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Windows, macOS or Linux with Docker, for a copy on your own computer

Use case | Who | What they get back
Search for scales | Researchers | Matching scales from published questionnaires, surveys and tests
Share a search | Research teams | A share link, which exists only when the usage tracking database is set up

How to set it up: Online use needs nothing, since the Space runs in the browser. A copy on your own computer needs Docker, and the app expects a set of environment variables.

• Python and pip, to download the files with the Hugging Face tool
• Docker on Windows, macOS or Linux
• MODEL__ITEM_MODEL_PATH and MODEL__SCALE_MODEL_PATH: Hugging Face model repository paths
• MODEL__ITEM_MODEL_ACCESS_TOKEN and MODEL__SCALE_MODEL_ACCESS_TOKEN: access tokens, for a private model
• DATA__DATASET_PATH: the Hugging Face dataset repository path
• DATA__ENCRYPTION_KEY: the encryption key for the database
• TRACKING_DB__REST_URL, TRACKING_DB__ANON_KEY and TRACKING_DB__JWT_TOKEN: the usage tracking database endpoint and its keys
• TRACKING_DB__ENABLED: true or false, and true when unset

1. Install the Hugging Face hub package.
2. Download the Space's files into a local folder.
3. Move into that folder.
4. Build the Docker image.
5. Run the container with port 7860 open.

pip install -U huggingface_hub
hf download magnolia-psychometrics/synthometricon --repo-type space --local-dir synthometricon
cd synthometricon
docker build -t synthometricon .
docker run -it -p 7860:7860 synthometricon

On Hugging Face, the variables go in the Space settings under Repository secrets. An optional ANALYTICS__WEBSITE_ID variable, set as a Space variable, switches on an Umami tracker.

How to use it: Open the Space's page, or the port 7860 page of your container, and search the collection of scales. The command that starts a local copy is this one.

docker run -it -p 7860:7860 synthometricon

Example: You open the page and search for a concept you want to measure. The app returns matching scales drawn from published questionnaires, surveys and tests.

For newcomers and experts: If you are new to this, open the Space's page and try a short search on a topic you know. Nothing needs installing, and you will see what a scale looks like in the results.

If you know the field, the Space names two models, surveybot3000 and a sentence-transformers model. Database changes are applied by hand as SQL files, in order, in a Supabase SQL editor. Those files live only in the project's GitHub repository, not in the Space. Without the tracking migration, searches still work but no share links appear.

Open the Space or run the Docker container
You type what you want to measure
The named models search the scales
Matching scales come back
The tracking database stores the search for sharing

Good to know: The authors cite a manuscript titled The Synthetic Nomological Net, which is in preparation.

• License: MIT, as the Space's license line says
• Cost to run: the hosted copy uses cpu-basic hardware at Hugging Face. A copy needs your own Docker setup, a tracking database endpoint with its keys and a database encryption key. An access token is needed only for a private model
• Data it reaches: the model and dataset repositories on Hugging Face, an encrypted database and the usage tracking database that records searches

On Hugging Face, 13 November 2026

• Likes: 11
• Built with: docker
• License: mit

Links

• Space: https://huggingface.co/spaces/magnolia-psychometrics/synthometricon
• Files: https://huggingface.co/spaces/magnolia-psychometrics/synthometricon/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.